© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4104
    Prev
    Next
    INDEX
    Explanations

    references to functional programming concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code documentation/annotations

    np_acts-logits-general · gemini-2.0-flash

    documentation structure markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mukaan
    -0.41
    لت
    -0.41
     https
    -0.39
    wigs
    -0.39
    onan
    -0.38
    isio
    -0.38
     structural
    -0.38
    ラー
    -0.37
     
    -0.37
    zeln
    -0.37
    POSITIVE LOGITS
     kasarigan
    1.08
    SourceChecksum
    0.85
     estekak
    0.84
     Normdatei
    0.84
    Datuak
    0.82
     ujednoznacz
    0.79
     linkovi
    0.79
    expandindo
    0.79
    Personensuche
    0.79
     الحره
    0.78
    Activations Density 0.175%

    No Known Activations